...
首页> 外文期刊>Information Theory, IEEE Transactions on >Minimization Problems Based on Relative src='/images/tex/25750.gif' alt='alpha '> -Entropy II: Reverse Projection
【24h】

Minimization Problems Based on Relative src='/images/tex/25750.gif' alt='alpha '> -Entropy II: Reverse Projection

机译:基于相对 src =“ / images / tex / 25750.gif” alt =“ alpha”> -熵II:反投影

获取原文
获取原文并翻译 | 示例
           

摘要

In part I of this two-part work, certain minimization problems based on a parametric family of relative entropies (denoted ) were studied. Such minimizers were called forward -projections. Here, a complementary class of minimization problems leading to the so-called reverse -projections are studied. Reverse -projections, particularly on log-convex or power-law families, are of interest in robust estimation problems () and in constrained compression settings (). Orthogonality of the power-law family with an associated linear family is first established and is then exploited to turn a reverse -projection into a forward -projection. The transformed problem is a simpler quasi-convex minimization subject to linear constraints.
机译:在这个由两部分组成的工作的第一部分中,研究了基于相对熵(表示为)的参数族的某些最小化问题。这种最小化器称为前向投影。在这里,研究了导致所谓的反向投影的最小化问题的补充类。反投影,尤其是在对数凸或幂律族上,对鲁棒估计问题()和受约束的压缩设置()感兴趣。首先建立幂律族与相关联的线性族的正交性,然后利用正交性将反投影变为正投影。变换后的问题是受线性约束的更简单的准凸极小化。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号